© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 23
    Prev
    Next
    INDEX
    Explanations

    code, numbers, and lists

    np_acts-logits-general · gemini-2.5-flash-lite

    The neuron specifically detects numeric tokens or sequences of digits (i.e. literal numbers) in the text.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    thalten
    -1.08
    bilang
    -1.02
    ーい
    -1.02
     lances
    -1.00
     eſt
    -0.99
    內容簡介
    -0.98
    ﹢
    -0.97
     coser
    -0.96
     菇
    -0.96
     現貨
    -0.94
    POSITIVE LOGITS
     ii
    1.01
     said
    0.99
     any
    0.96
     with
    0.94
     eenige
    0.94
     ..
    0.93
    ɑ
    0.93
     two
    0.92
     In
    0.90
     since
    0.90
    Activations Density 0.001%

    No Known Activations